Safetensors
English
llama
Jeremy Greer commited on
Commit
92f9752
·
1 Parent(s): 33883c1

Add remaining configs

Browse files
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.48.0"
12
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 4096,
2062
+ "pad_token": "<|finetune_right_pad_id|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
trainer_state.json ADDED
@@ -0,0 +1,2033 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 300,
6
+ "global_step": 2411,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00414765657403567,
13
+ "grad_norm": 1.9609375,
14
+ "learning_rate": 1.6666666666666667e-05,
15
+ "loss": 0.3119,
16
+ "num_input_tokens_seen": 1693136,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.00829531314807134,
21
+ "grad_norm": 1.75,
22
+ "learning_rate": 3.3333333333333335e-05,
23
+ "loss": 0.1145,
24
+ "num_input_tokens_seen": 3345072,
25
+ "step": 20
26
+ },
27
+ {
28
+ "epoch": 0.01244296972210701,
29
+ "grad_norm": 1.4765625,
30
+ "learning_rate": 3.999937641573031e-05,
31
+ "loss": 0.108,
32
+ "num_input_tokens_seen": 4962592,
33
+ "step": 30
34
+ },
35
+ {
36
+ "epoch": 0.01659062629614268,
37
+ "grad_norm": 1.28125,
38
+ "learning_rate": 3.999556576379093e-05,
39
+ "loss": 0.0925,
40
+ "num_input_tokens_seen": 6599360,
41
+ "step": 40
42
+ },
43
+ {
44
+ "epoch": 0.02073828287017835,
45
+ "grad_norm": 2.578125,
46
+ "learning_rate": 3.998829155488428e-05,
47
+ "loss": 0.1203,
48
+ "num_input_tokens_seen": 8134112,
49
+ "step": 50
50
+ },
51
+ {
52
+ "epoch": 0.02488593944421402,
53
+ "grad_norm": 1.1953125,
54
+ "learning_rate": 3.997755504902156e-05,
55
+ "loss": 0.1231,
56
+ "num_input_tokens_seen": 9757824,
57
+ "step": 60
58
+ },
59
+ {
60
+ "epoch": 0.02903359601824969,
61
+ "grad_norm": 1.0234375,
62
+ "learning_rate": 3.9963358105940094e-05,
63
+ "loss": 0.0984,
64
+ "num_input_tokens_seen": 11420880,
65
+ "step": 70
66
+ },
67
+ {
68
+ "epoch": 0.03318125259228536,
69
+ "grad_norm": 1.53125,
70
+ "learning_rate": 3.9945703184781146e-05,
71
+ "loss": 0.0918,
72
+ "num_input_tokens_seen": 13082688,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 0.03732890916632103,
77
+ "grad_norm": 1.1875,
78
+ "learning_rate": 3.9924593343664e-05,
79
+ "loss": 0.0755,
80
+ "num_input_tokens_seen": 14714672,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 0.0414765657403567,
85
+ "grad_norm": 1.1328125,
86
+ "learning_rate": 3.990003223915623e-05,
87
+ "loss": 0.0805,
88
+ "num_input_tokens_seen": 16339072,
89
+ "step": 100
90
+ },
91
+ {
92
+ "epoch": 0.045624222314392365,
93
+ "grad_norm": 0.87890625,
94
+ "learning_rate": 3.9872024125640315e-05,
95
+ "loss": 0.0869,
96
+ "num_input_tokens_seen": 17948576,
97
+ "step": 110
98
+ },
99
+ {
100
+ "epoch": 0.04977187888842804,
101
+ "grad_norm": 1.8515625,
102
+ "learning_rate": 3.9840573854576696e-05,
103
+ "loss": 0.081,
104
+ "num_input_tokens_seen": 19523632,
105
+ "step": 120
106
+ },
107
+ {
108
+ "epoch": 0.05391953546246371,
109
+ "grad_norm": 1.25,
110
+ "learning_rate": 3.980568687366349e-05,
111
+ "loss": 0.0843,
112
+ "num_input_tokens_seen": 21150112,
113
+ "step": 130
114
+ },
115
+ {
116
+ "epoch": 0.05806719203649938,
117
+ "grad_norm": 3.21875,
118
+ "learning_rate": 3.976736922589278e-05,
119
+ "loss": 0.0837,
120
+ "num_input_tokens_seen": 22802656,
121
+ "step": 140
122
+ },
123
+ {
124
+ "epoch": 0.06221484861053505,
125
+ "grad_norm": 1.0859375,
126
+ "learning_rate": 3.972562754850392e-05,
127
+ "loss": 0.1104,
128
+ "num_input_tokens_seen": 24427648,
129
+ "step": 150
130
+ },
131
+ {
132
+ "epoch": 0.06636250518457072,
133
+ "grad_norm": 1.0625,
134
+ "learning_rate": 3.968046907183383e-05,
135
+ "loss": 0.102,
136
+ "num_input_tokens_seen": 26034736,
137
+ "step": 160
138
+ },
139
+ {
140
+ "epoch": 0.07051016175860639,
141
+ "grad_norm": 0.97265625,
142
+ "learning_rate": 3.963190161806461e-05,
143
+ "loss": 0.0808,
144
+ "num_input_tokens_seen": 27653024,
145
+ "step": 170
146
+ },
147
+ {
148
+ "epoch": 0.07465781833264205,
149
+ "grad_norm": 1.0078125,
150
+ "learning_rate": 3.9579933599868605e-05,
151
+ "loss": 0.0771,
152
+ "num_input_tokens_seen": 29276352,
153
+ "step": 180
154
+ },
155
+ {
156
+ "epoch": 0.07880547490667773,
157
+ "grad_norm": 1.9921875,
158
+ "learning_rate": 3.952457401895115e-05,
159
+ "loss": 0.0809,
160
+ "num_input_tokens_seen": 30896032,
161
+ "step": 190
162
+ },
163
+ {
164
+ "epoch": 0.0829531314807134,
165
+ "grad_norm": 0.671875,
166
+ "learning_rate": 3.9465832464491406e-05,
167
+ "loss": 0.0724,
168
+ "num_input_tokens_seen": 32445728,
169
+ "step": 200
170
+ },
171
+ {
172
+ "epoch": 0.08710078805474906,
173
+ "grad_norm": 1.0,
174
+ "learning_rate": 3.9403719111481295e-05,
175
+ "loss": 0.0753,
176
+ "num_input_tokens_seen": 34058864,
177
+ "step": 210
178
+ },
179
+ {
180
+ "epoch": 0.09124844462878473,
181
+ "grad_norm": 0.828125,
182
+ "learning_rate": 3.933824471896305e-05,
183
+ "loss": 0.079,
184
+ "num_input_tokens_seen": 35664048,
185
+ "step": 220
186
+ },
187
+ {
188
+ "epoch": 0.09539610120282041,
189
+ "grad_norm": 1.53125,
190
+ "learning_rate": 3.926942062816558e-05,
191
+ "loss": 0.078,
192
+ "num_input_tokens_seen": 37250864,
193
+ "step": 230
194
+ },
195
+ {
196
+ "epoch": 0.09954375777685608,
197
+ "grad_norm": 2.21875,
198
+ "learning_rate": 3.919725876053997e-05,
199
+ "loss": 0.0762,
200
+ "num_input_tokens_seen": 38878368,
201
+ "step": 240
202
+ },
203
+ {
204
+ "epoch": 0.10369141435089174,
205
+ "grad_norm": 0.94921875,
206
+ "learning_rate": 3.9121771615694496e-05,
207
+ "loss": 0.0812,
208
+ "num_input_tokens_seen": 40446704,
209
+ "step": 250
210
+ },
211
+ {
212
+ "epoch": 0.10783907092492742,
213
+ "grad_norm": 1.046875,
214
+ "learning_rate": 3.90429722692295e-05,
215
+ "loss": 0.09,
216
+ "num_input_tokens_seen": 42044128,
217
+ "step": 260
218
+ },
219
+ {
220
+ "epoch": 0.11198672749896309,
221
+ "grad_norm": 1.2578125,
222
+ "learning_rate": 3.8960874370472476e-05,
223
+ "loss": 0.0744,
224
+ "num_input_tokens_seen": 43653376,
225
+ "step": 270
226
+ },
227
+ {
228
+ "epoch": 0.11613438407299875,
229
+ "grad_norm": 0.7578125,
230
+ "learning_rate": 3.887549214011378e-05,
231
+ "loss": 0.0822,
232
+ "num_input_tokens_seen": 45249536,
233
+ "step": 280
234
+ },
235
+ {
236
+ "epoch": 0.12028204064703442,
237
+ "grad_norm": 0.94921875,
238
+ "learning_rate": 3.878684036774337e-05,
239
+ "loss": 0.0673,
240
+ "num_input_tokens_seen": 46861728,
241
+ "step": 290
242
+ },
243
+ {
244
+ "epoch": 0.1244296972210701,
245
+ "grad_norm": 1.390625,
246
+ "learning_rate": 3.869493440928904e-05,
247
+ "loss": 0.0969,
248
+ "num_input_tokens_seen": 48483088,
249
+ "step": 300
250
+ },
251
+ {
252
+ "epoch": 0.1244296972210701,
253
+ "eval_loss": 0.07887571305036545,
254
+ "eval_runtime": 51.9245,
255
+ "eval_samples_per_second": 60.029,
256
+ "eval_steps_per_second": 1.887,
257
+ "num_input_tokens_seen": 48483088,
258
+ "step": 300
259
+ },
260
+ {
261
+ "epoch": 0.12857735379510576,
262
+ "grad_norm": 1.0703125,
263
+ "learning_rate": 3.859979018435648e-05,
264
+ "loss": 0.0703,
265
+ "num_input_tokens_seen": 50105600,
266
+ "step": 310
267
+ },
268
+ {
269
+ "epoch": 0.13272501036914144,
270
+ "grad_norm": 0.74609375,
271
+ "learning_rate": 3.8501424173471795e-05,
272
+ "loss": 0.073,
273
+ "num_input_tokens_seen": 51741392,
274
+ "step": 320
275
+ },
276
+ {
277
+ "epoch": 0.1368726669431771,
278
+ "grad_norm": 0.8828125,
279
+ "learning_rate": 3.839985341522674e-05,
280
+ "loss": 0.089,
281
+ "num_input_tokens_seen": 53360288,
282
+ "step": 330
283
+ },
284
+ {
285
+ "epoch": 0.14102032351721278,
286
+ "grad_norm": 0.84765625,
287
+ "learning_rate": 3.829509550332743e-05,
288
+ "loss": 0.0805,
289
+ "num_input_tokens_seen": 55027488,
290
+ "step": 340
291
+ },
292
+ {
293
+ "epoch": 0.14516798009124846,
294
+ "grad_norm": 0.75,
295
+ "learning_rate": 3.818716858354677e-05,
296
+ "loss": 0.0771,
297
+ "num_input_tokens_seen": 56654080,
298
+ "step": 350
299
+ },
300
+ {
301
+ "epoch": 0.1493156366652841,
302
+ "grad_norm": 0.984375,
303
+ "learning_rate": 3.807609135058135e-05,
304
+ "loss": 0.0877,
305
+ "num_input_tokens_seen": 58311408,
306
+ "step": 360
307
+ },
308
+ {
309
+ "epoch": 0.1534632932393198,
310
+ "grad_norm": 0.78125,
311
+ "learning_rate": 3.796188304481319e-05,
312
+ "loss": 0.0755,
313
+ "num_input_tokens_seen": 59931536,
314
+ "step": 370
315
+ },
316
+ {
317
+ "epoch": 0.15761094981335547,
318
+ "grad_norm": 0.71484375,
319
+ "learning_rate": 3.784456344897702e-05,
320
+ "loss": 0.0894,
321
+ "num_input_tokens_seen": 61618192,
322
+ "step": 380
323
+ },
324
+ {
325
+ "epoch": 0.16175860638739112,
326
+ "grad_norm": 0.9453125,
327
+ "learning_rate": 3.772415288473357e-05,
328
+ "loss": 0.0918,
329
+ "num_input_tokens_seen": 63241440,
330
+ "step": 390
331
+ },
332
+ {
333
+ "epoch": 0.1659062629614268,
334
+ "grad_norm": 1.2265625,
335
+ "learning_rate": 3.7600672209149535e-05,
336
+ "loss": 0.0749,
337
+ "num_input_tokens_seen": 64840016,
338
+ "step": 400
339
+ },
340
+ {
341
+ "epoch": 0.17005391953546245,
342
+ "grad_norm": 1.0078125,
343
+ "learning_rate": 3.747414281108478e-05,
344
+ "loss": 0.0748,
345
+ "num_input_tokens_seen": 66494144,
346
+ "step": 410
347
+ },
348
+ {
349
+ "epoch": 0.17420157610949813,
350
+ "grad_norm": 0.69921875,
351
+ "learning_rate": 3.734458660748748e-05,
352
+ "loss": 0.0775,
353
+ "num_input_tokens_seen": 68099408,
354
+ "step": 420
355
+ },
356
+ {
357
+ "epoch": 0.1783492326835338,
358
+ "grad_norm": 1.6953125,
359
+ "learning_rate": 3.721202603959768e-05,
360
+ "loss": 0.0779,
361
+ "num_input_tokens_seen": 69714944,
362
+ "step": 430
363
+ },
364
+ {
365
+ "epoch": 0.18249688925756946,
366
+ "grad_norm": 0.73828125,
367
+ "learning_rate": 3.7076484069060195e-05,
368
+ "loss": 0.0789,
369
+ "num_input_tokens_seen": 71316448,
370
+ "step": 440
371
+ },
372
+ {
373
+ "epoch": 0.18664454583160514,
374
+ "grad_norm": 0.6171875,
375
+ "learning_rate": 3.69379841739472e-05,
376
+ "loss": 0.0749,
377
+ "num_input_tokens_seen": 72954352,
378
+ "step": 450
379
+ },
380
+ {
381
+ "epoch": 0.19079220240564082,
382
+ "grad_norm": 1.1328125,
383
+ "learning_rate": 3.6796550344691495e-05,
384
+ "loss": 0.0746,
385
+ "num_input_tokens_seen": 74556368,
386
+ "step": 460
387
+ },
388
+ {
389
+ "epoch": 0.19493985897967647,
390
+ "grad_norm": 1.375,
391
+ "learning_rate": 3.6652207079930956e-05,
392
+ "loss": 0.084,
393
+ "num_input_tokens_seen": 76204704,
394
+ "step": 470
395
+ },
396
+ {
397
+ "epoch": 0.19908751555371215,
398
+ "grad_norm": 1.046875,
399
+ "learning_rate": 3.6504979382264966e-05,
400
+ "loss": 0.0705,
401
+ "num_input_tokens_seen": 77820544,
402
+ "step": 480
403
+ },
404
+ {
405
+ "epoch": 0.20323517212774783,
406
+ "grad_norm": 0.58203125,
407
+ "learning_rate": 3.6354892753923574e-05,
408
+ "loss": 0.0709,
409
+ "num_input_tokens_seen": 79449040,
410
+ "step": 490
411
+ },
412
+ {
413
+ "epoch": 0.20738282870178348,
414
+ "grad_norm": 0.59375,
415
+ "learning_rate": 3.620197319235009e-05,
416
+ "loss": 0.0796,
417
+ "num_input_tokens_seen": 81052496,
418
+ "step": 500
419
+ },
420
+ {
421
+ "epoch": 0.21153048527581916,
422
+ "grad_norm": 1.0546875,
423
+ "learning_rate": 3.604624718569789e-05,
424
+ "loss": 0.0854,
425
+ "num_input_tokens_seen": 82677824,
426
+ "step": 510
427
+ },
428
+ {
429
+ "epoch": 0.21567814184985484,
430
+ "grad_norm": 0.78515625,
431
+ "learning_rate": 3.588774170824225e-05,
432
+ "loss": 0.0729,
433
+ "num_input_tokens_seen": 84295712,
434
+ "step": 520
435
+ },
436
+ {
437
+ "epoch": 0.2198257984238905,
438
+ "grad_norm": 1.2890625,
439
+ "learning_rate": 3.572648421570799e-05,
440
+ "loss": 0.0705,
441
+ "num_input_tokens_seen": 85914864,
442
+ "step": 530
443
+ },
444
+ {
445
+ "epoch": 0.22397345499792617,
446
+ "grad_norm": 0.671875,
447
+ "learning_rate": 3.5562502640513625e-05,
448
+ "loss": 0.0723,
449
+ "num_input_tokens_seen": 87477280,
450
+ "step": 540
451
+ },
452
+ {
453
+ "epoch": 0.22812111157196185,
454
+ "grad_norm": 1.0859375,
455
+ "learning_rate": 3.5395825386933086e-05,
456
+ "loss": 0.0719,
457
+ "num_input_tokens_seen": 89076752,
458
+ "step": 550
459
+ },
460
+ {
461
+ "epoch": 0.2322687681459975,
462
+ "grad_norm": 0.66796875,
463
+ "learning_rate": 3.522648132617561e-05,
464
+ "loss": 0.0696,
465
+ "num_input_tokens_seen": 90756528,
466
+ "step": 560
467
+ },
468
+ {
469
+ "epoch": 0.23641642472003319,
470
+ "grad_norm": 1.140625,
471
+ "learning_rate": 3.505449979138478e-05,
472
+ "loss": 0.0567,
473
+ "num_input_tokens_seen": 92354288,
474
+ "step": 570
475
+ },
476
+ {
477
+ "epoch": 0.24056408129406884,
478
+ "grad_norm": 0.9140625,
479
+ "learning_rate": 3.4879910572557544e-05,
480
+ "loss": 0.085,
481
+ "num_input_tokens_seen": 93981696,
482
+ "step": 580
483
+ },
484
+ {
485
+ "epoch": 0.24471173786810452,
486
+ "grad_norm": 0.62109375,
487
+ "learning_rate": 3.4702743911384093e-05,
488
+ "loss": 0.0763,
489
+ "num_input_tokens_seen": 95603856,
490
+ "step": 590
491
+ },
492
+ {
493
+ "epoch": 0.2488593944421402,
494
+ "grad_norm": 0.578125,
495
+ "learning_rate": 3.452303049600954e-05,
496
+ "loss": 0.0617,
497
+ "num_input_tokens_seen": 97194624,
498
+ "step": 600
499
+ },
500
+ {
501
+ "epoch": 0.2488593944421402,
502
+ "eval_loss": 0.07688611000776291,
503
+ "eval_runtime": 52.396,
504
+ "eval_samples_per_second": 59.489,
505
+ "eval_steps_per_second": 1.87,
506
+ "num_input_tokens_seen": 97194624,
507
+ "step": 600
508
+ },
509
+ {
510
+ "epoch": 0.2530070510161759,
511
+ "grad_norm": 1.3359375,
512
+ "learning_rate": 3.434080145571823e-05,
513
+ "loss": 0.0708,
514
+ "num_input_tokens_seen": 98803440,
515
+ "step": 610
516
+ },
517
+ {
518
+ "epoch": 0.25715470759021153,
519
+ "grad_norm": 0.56640625,
520
+ "learning_rate": 3.4156088355541595e-05,
521
+ "loss": 0.0562,
522
+ "num_input_tokens_seen": 100369952,
523
+ "step": 620
524
+ },
525
+ {
526
+ "epoch": 0.2613023641642472,
527
+ "grad_norm": 0.90234375,
528
+ "learning_rate": 3.3968923190790616e-05,
529
+ "loss": 0.0699,
530
+ "num_input_tokens_seen": 102025584,
531
+ "step": 630
532
+ },
533
+ {
534
+ "epoch": 0.2654500207382829,
535
+ "grad_norm": 0.8203125,
536
+ "learning_rate": 3.377933838151374e-05,
537
+ "loss": 0.0618,
538
+ "num_input_tokens_seen": 103615424,
539
+ "step": 640
540
+ },
541
+ {
542
+ "epoch": 0.26959767731231854,
543
+ "grad_norm": 0.5859375,
544
+ "learning_rate": 3.358736676688113e-05,
545
+ "loss": 0.0627,
546
+ "num_input_tokens_seen": 105236720,
547
+ "step": 650
548
+ },
549
+ {
550
+ "epoch": 0.2737453338863542,
551
+ "grad_norm": 0.58203125,
552
+ "learning_rate": 3.339304159949648e-05,
553
+ "loss": 0.0659,
554
+ "num_input_tokens_seen": 106863168,
555
+ "step": 660
556
+ },
557
+ {
558
+ "epoch": 0.2778929904603899,
559
+ "grad_norm": 0.6875,
560
+ "learning_rate": 3.3196396539637015e-05,
561
+ "loss": 0.0619,
562
+ "num_input_tokens_seen": 108445968,
563
+ "step": 670
564
+ },
565
+ {
566
+ "epoch": 0.28204064703442555,
567
+ "grad_norm": 1.09375,
568
+ "learning_rate": 3.299746564942309e-05,
569
+ "loss": 0.0757,
570
+ "num_input_tokens_seen": 110128992,
571
+ "step": 680
572
+ },
573
+ {
574
+ "epoch": 0.2861883036084612,
575
+ "grad_norm": 0.66015625,
576
+ "learning_rate": 3.279628338691798e-05,
577
+ "loss": 0.0548,
578
+ "num_input_tokens_seen": 111745104,
579
+ "step": 690
580
+ },
581
+ {
582
+ "epoch": 0.2903359601824969,
583
+ "grad_norm": 0.6171875,
584
+ "learning_rate": 3.259288460015927e-05,
585
+ "loss": 0.0747,
586
+ "num_input_tokens_seen": 113351136,
587
+ "step": 700
588
+ },
589
+ {
590
+ "epoch": 0.29448361675653256,
591
+ "grad_norm": 0.8125,
592
+ "learning_rate": 3.238730452112256e-05,
593
+ "loss": 0.0761,
594
+ "num_input_tokens_seen": 115000912,
595
+ "step": 710
596
+ },
597
+ {
598
+ "epoch": 0.2986312733305682,
599
+ "grad_norm": 0.78125,
600
+ "learning_rate": 3.217957875961871e-05,
601
+ "loss": 0.067,
602
+ "num_input_tokens_seen": 116617280,
603
+ "step": 720
604
+ },
605
+ {
606
+ "epoch": 0.3027789299046039,
607
+ "grad_norm": 0.7265625,
608
+ "learning_rate": 3.196974329712567e-05,
609
+ "loss": 0.0687,
610
+ "num_input_tokens_seen": 118217968,
611
+ "step": 730
612
+ },
613
+ {
614
+ "epoch": 0.3069265864786396,
615
+ "grad_norm": 0.68359375,
616
+ "learning_rate": 3.1757834480555885e-05,
617
+ "loss": 0.0596,
618
+ "num_input_tokens_seen": 119844304,
619
+ "step": 740
620
+ },
621
+ {
622
+ "epoch": 0.3110742430526752,
623
+ "grad_norm": 0.94140625,
624
+ "learning_rate": 3.1543889015960416e-05,
625
+ "loss": 0.0728,
626
+ "num_input_tokens_seen": 121474288,
627
+ "step": 750
628
+ },
629
+ {
630
+ "epoch": 0.31522189962671093,
631
+ "grad_norm": 0.56640625,
632
+ "learning_rate": 3.1327943962170874e-05,
633
+ "loss": 0.066,
634
+ "num_input_tokens_seen": 123105712,
635
+ "step": 760
636
+ },
637
+ {
638
+ "epoch": 0.3193695562007466,
639
+ "grad_norm": 0.58203125,
640
+ "learning_rate": 3.111003672438022e-05,
641
+ "loss": 0.0709,
642
+ "num_input_tokens_seen": 124692896,
643
+ "step": 770
644
+ },
645
+ {
646
+ "epoch": 0.32351721277478224,
647
+ "grad_norm": 0.71484375,
648
+ "learning_rate": 3.089020504766356e-05,
649
+ "loss": 0.0597,
650
+ "num_input_tokens_seen": 126346784,
651
+ "step": 780
652
+ },
653
+ {
654
+ "epoch": 0.32766486934881794,
655
+ "grad_norm": 0.76171875,
656
+ "learning_rate": 3.0668487010440105e-05,
657
+ "loss": 0.0692,
658
+ "num_input_tokens_seen": 127969872,
659
+ "step": 790
660
+ },
661
+ {
662
+ "epoch": 0.3318125259228536,
663
+ "grad_norm": 0.58203125,
664
+ "learning_rate": 3.0444921017877357e-05,
665
+ "loss": 0.0607,
666
+ "num_input_tokens_seen": 129520000,
667
+ "step": 800
668
+ },
669
+ {
670
+ "epoch": 0.33596018249688925,
671
+ "grad_norm": 0.482421875,
672
+ "learning_rate": 3.021954579523874e-05,
673
+ "loss": 0.0592,
674
+ "num_input_tokens_seen": 131142560,
675
+ "step": 810
676
+ },
677
+ {
678
+ "epoch": 0.3401078390709249,
679
+ "grad_norm": 0.7734375,
680
+ "learning_rate": 2.99924003811757e-05,
681
+ "loss": 0.0719,
682
+ "num_input_tokens_seen": 132757520,
683
+ "step": 820
684
+ },
685
+ {
686
+ "epoch": 0.3442554956449606,
687
+ "grad_norm": 0.78125,
688
+ "learning_rate": 2.976352412096563e-05,
689
+ "loss": 0.0606,
690
+ "num_input_tokens_seen": 134374032,
691
+ "step": 830
692
+ },
693
+ {
694
+ "epoch": 0.34840315221899626,
695
+ "grad_norm": 2.4375,
696
+ "learning_rate": 2.9532956659696594e-05,
697
+ "loss": 0.0519,
698
+ "num_input_tokens_seen": 135996944,
699
+ "step": 840
700
+ },
701
+ {
702
+ "epoch": 0.3525508087930319,
703
+ "grad_norm": 0.87890625,
704
+ "learning_rate": 2.930073793540017e-05,
705
+ "loss": 0.0579,
706
+ "num_input_tokens_seen": 137587472,
707
+ "step": 850
708
+ },
709
+ {
710
+ "epoch": 0.3566984653670676,
711
+ "grad_norm": 2.125,
712
+ "learning_rate": 2.9066908172133544e-05,
713
+ "loss": 0.0648,
714
+ "num_input_tokens_seen": 139190208,
715
+ "step": 860
716
+ },
717
+ {
718
+ "epoch": 0.36084612194110327,
719
+ "grad_norm": 1.3984375,
720
+ "learning_rate": 2.8831507873012006e-05,
721
+ "loss": 0.0677,
722
+ "num_input_tokens_seen": 140807968,
723
+ "step": 870
724
+ },
725
+ {
726
+ "epoch": 0.3649937785151389,
727
+ "grad_norm": 1.1796875,
728
+ "learning_rate": 2.85945778131932e-05,
729
+ "loss": 0.0549,
730
+ "num_input_tokens_seen": 142402656,
731
+ "step": 880
732
+ },
733
+ {
734
+ "epoch": 0.36914143508917463,
735
+ "grad_norm": 0.703125,
736
+ "learning_rate": 2.835615903281418e-05,
737
+ "loss": 0.0543,
738
+ "num_input_tokens_seen": 143979168,
739
+ "step": 890
740
+ },
741
+ {
742
+ "epoch": 0.3732890916632103,
743
+ "grad_norm": 0.72265625,
744
+ "learning_rate": 2.8116292829882606e-05,
745
+ "loss": 0.0779,
746
+ "num_input_tokens_seen": 145588016,
747
+ "step": 900
748
+ },
749
+ {
750
+ "epoch": 0.3732890916632103,
751
+ "eval_loss": 0.06259813904762268,
752
+ "eval_runtime": 52.0703,
753
+ "eval_samples_per_second": 59.861,
754
+ "eval_steps_per_second": 1.882,
755
+ "num_input_tokens_seen": 145588016,
756
+ "step": 900
757
+ },
758
+ {
759
+ "epoch": 0.37743674823724593,
760
+ "grad_norm": 1.0390625,
761
+ "learning_rate": 2.7875020753123222e-05,
762
+ "loss": 0.0628,
763
+ "num_input_tokens_seen": 147239120,
764
+ "step": 910
765
+ },
766
+ {
767
+ "epoch": 0.38158440481128164,
768
+ "grad_norm": 0.6953125,
769
+ "learning_rate": 2.7632384594781006e-05,
770
+ "loss": 0.0701,
771
+ "num_input_tokens_seen": 148837248,
772
+ "step": 920
773
+ },
774
+ {
775
+ "epoch": 0.3857320613853173,
776
+ "grad_norm": 0.640625,
777
+ "learning_rate": 2.7388426383381997e-05,
778
+ "loss": 0.0578,
779
+ "num_input_tokens_seen": 150442016,
780
+ "step": 930
781
+ },
782
+ {
783
+ "epoch": 0.38987971795935294,
784
+ "grad_norm": 0.56640625,
785
+ "learning_rate": 2.7143188376453346e-05,
786
+ "loss": 0.0591,
787
+ "num_input_tokens_seen": 152046160,
788
+ "step": 940
789
+ },
790
+ {
791
+ "epoch": 0.39402737453338865,
792
+ "grad_norm": 0.66015625,
793
+ "learning_rate": 2.6896713053203564e-05,
794
+ "loss": 0.0649,
795
+ "num_input_tokens_seen": 153639888,
796
+ "step": 950
797
+ },
798
+ {
799
+ "epoch": 0.3981750311074243,
800
+ "grad_norm": 0.734375,
801
+ "learning_rate": 2.664904310716446e-05,
802
+ "loss": 0.0567,
803
+ "num_input_tokens_seen": 155299264,
804
+ "step": 960
805
+ },
806
+ {
807
+ "epoch": 0.40232268768145996,
808
+ "grad_norm": 0.53515625,
809
+ "learning_rate": 2.6400221438795938e-05,
810
+ "loss": 0.0659,
811
+ "num_input_tokens_seen": 156933648,
812
+ "step": 970
813
+ },
814
+ {
815
+ "epoch": 0.40647034425549566,
816
+ "grad_norm": 0.59375,
817
+ "learning_rate": 2.6150291148054923e-05,
818
+ "loss": 0.0495,
819
+ "num_input_tokens_seen": 158474752,
820
+ "step": 980
821
+ },
822
+ {
823
+ "epoch": 0.4106180008295313,
824
+ "grad_norm": 0.55859375,
825
+ "learning_rate": 2.5899295526929758e-05,
826
+ "loss": 0.0561,
827
+ "num_input_tokens_seen": 160089840,
828
+ "step": 990
829
+ },
830
+ {
831
+ "epoch": 0.41476565740356697,
832
+ "grad_norm": 1.234375,
833
+ "learning_rate": 2.5647278051941298e-05,
834
+ "loss": 0.069,
835
+ "num_input_tokens_seen": 161694944,
836
+ "step": 1000
837
+ },
838
+ {
839
+ "epoch": 0.4189133139776027,
840
+ "grad_norm": 0.470703125,
841
+ "learning_rate": 2.5394282376612132e-05,
842
+ "loss": 0.056,
843
+ "num_input_tokens_seen": 163300880,
844
+ "step": 1010
845
+ },
846
+ {
847
+ "epoch": 0.4230609705516383,
848
+ "grad_norm": 0.62890625,
849
+ "learning_rate": 2.5140352323905016e-05,
850
+ "loss": 0.0585,
851
+ "num_input_tokens_seen": 164947744,
852
+ "step": 1020
853
+ },
854
+ {
855
+ "epoch": 0.427208627125674,
856
+ "grad_norm": 0.69140625,
857
+ "learning_rate": 2.4885531878632066e-05,
858
+ "loss": 0.0632,
859
+ "num_input_tokens_seen": 166554016,
860
+ "step": 1030
861
+ },
862
+ {
863
+ "epoch": 0.4313562836997097,
864
+ "grad_norm": 0.51953125,
865
+ "learning_rate": 2.4629865179835863e-05,
866
+ "loss": 0.0744,
867
+ "num_input_tokens_seen": 168185136,
868
+ "step": 1040
869
+ },
870
+ {
871
+ "epoch": 0.43550394027374534,
872
+ "grad_norm": 0.5703125,
873
+ "learning_rate": 2.4373396513143844e-05,
874
+ "loss": 0.0514,
875
+ "num_input_tokens_seen": 169806336,
876
+ "step": 1050
877
+ },
878
+ {
879
+ "epoch": 0.439651596847781,
880
+ "grad_norm": 0.79296875,
881
+ "learning_rate": 2.4116170303097336e-05,
882
+ "loss": 0.0591,
883
+ "num_input_tokens_seen": 171421072,
884
+ "step": 1060
885
+ },
886
+ {
887
+ "epoch": 0.4437992534218167,
888
+ "grad_norm": 0.60546875,
889
+ "learning_rate": 2.3858231105456472e-05,
890
+ "loss": 0.0583,
891
+ "num_input_tokens_seen": 173001056,
892
+ "step": 1070
893
+ },
894
+ {
895
+ "epoch": 0.44794690999585235,
896
+ "grad_norm": 0.828125,
897
+ "learning_rate": 2.3599623599482418e-05,
898
+ "loss": 0.0494,
899
+ "num_input_tokens_seen": 174621744,
900
+ "step": 1080
901
+ },
902
+ {
903
+ "epoch": 0.452094566569888,
904
+ "grad_norm": 0.6328125,
905
+ "learning_rate": 2.334039258019823e-05,
906
+ "loss": 0.0557,
907
+ "num_input_tokens_seen": 176178848,
908
+ "step": 1090
909
+ },
910
+ {
911
+ "epoch": 0.4562422231439237,
912
+ "grad_norm": 0.75,
913
+ "learning_rate": 2.3080582950629574e-05,
914
+ "loss": 0.0512,
915
+ "num_input_tokens_seen": 177751392,
916
+ "step": 1100
917
+ },
918
+ {
919
+ "epoch": 0.46038987971795936,
920
+ "grad_norm": 0.69921875,
921
+ "learning_rate": 2.282023971402684e-05,
922
+ "loss": 0.056,
923
+ "num_input_tokens_seen": 179395408,
924
+ "step": 1110
925
+ },
926
+ {
927
+ "epoch": 0.464537536291995,
928
+ "grad_norm": 0.58203125,
929
+ "learning_rate": 2.2559407966069827e-05,
930
+ "loss": 0.0476,
931
+ "num_input_tokens_seen": 180974112,
932
+ "step": 1120
933
+ },
934
+ {
935
+ "epoch": 0.4686851928660307,
936
+ "grad_norm": 0.56640625,
937
+ "learning_rate": 2.2298132887056437e-05,
938
+ "loss": 0.07,
939
+ "num_input_tokens_seen": 182636064,
940
+ "step": 1130
941
+ },
942
+ {
943
+ "epoch": 0.47283284944006637,
944
+ "grad_norm": 0.75390625,
945
+ "learning_rate": 2.2036459734076715e-05,
946
+ "loss": 0.0481,
947
+ "num_input_tokens_seen": 184298640,
948
+ "step": 1140
949
+ },
950
+ {
951
+ "epoch": 0.476980506014102,
952
+ "grad_norm": 0.71875,
953
+ "learning_rate": 2.1774433833173577e-05,
954
+ "loss": 0.0526,
955
+ "num_input_tokens_seen": 185976832,
956
+ "step": 1150
957
+ },
958
+ {
959
+ "epoch": 0.4811281625881377,
960
+ "grad_norm": 0.75,
961
+ "learning_rate": 2.1512100571491636e-05,
962
+ "loss": 0.0605,
963
+ "num_input_tokens_seen": 187586816,
964
+ "step": 1160
965
+ },
966
+ {
967
+ "epoch": 0.4852758191621734,
968
+ "grad_norm": 0.87109375,
969
+ "learning_rate": 2.1249505389415372e-05,
970
+ "loss": 0.0598,
971
+ "num_input_tokens_seen": 189156864,
972
+ "step": 1170
973
+ },
974
+ {
975
+ "epoch": 0.48942347573620903,
976
+ "grad_norm": 0.375,
977
+ "learning_rate": 2.0986693772698133e-05,
978
+ "loss": 0.0426,
979
+ "num_input_tokens_seen": 190762160,
980
+ "step": 1180
981
+ },
982
+ {
983
+ "epoch": 0.4935711323102447,
984
+ "grad_norm": 0.67578125,
985
+ "learning_rate": 2.0723711244583274e-05,
986
+ "loss": 0.0473,
987
+ "num_input_tokens_seen": 192413488,
988
+ "step": 1190
989
+ },
990
+ {
991
+ "epoch": 0.4977187888842804,
992
+ "grad_norm": 0.466796875,
993
+ "learning_rate": 2.046060335791876e-05,
994
+ "loss": 0.0538,
995
+ "num_input_tokens_seen": 194012016,
996
+ "step": 1200
997
+ },
998
+ {
999
+ "epoch": 0.4977187888842804,
1000
+ "eval_loss": 0.05474493280053139,
1001
+ "eval_runtime": 52.0108,
1002
+ "eval_samples_per_second": 59.93,
1003
+ "eval_steps_per_second": 1.884,
1004
+ "num_input_tokens_seen": 194012016,
1005
+ "step": 1200
1006
+ },
1007
+ {
1008
+ "epoch": 0.501866445458316,
1009
+ "grad_norm": 0.54296875,
1010
+ "learning_rate": 2.0197415687266723e-05,
1011
+ "loss": 0.0555,
1012
+ "num_input_tokens_seen": 195645952,
1013
+ "step": 1210
1014
+ },
1015
+ {
1016
+ "epoch": 0.5060141020323518,
1017
+ "grad_norm": 0.625,
1018
+ "learning_rate": 1.9934193821009168e-05,
1019
+ "loss": 0.0431,
1020
+ "num_input_tokens_seen": 197272080,
1021
+ "step": 1220
1022
+ },
1023
+ {
1024
+ "epoch": 0.5101617586063873,
1025
+ "grad_norm": 0.66015625,
1026
+ "learning_rate": 1.967098335345132e-05,
1027
+ "loss": 0.0549,
1028
+ "num_input_tokens_seen": 198887696,
1029
+ "step": 1230
1030
+ },
1031
+ {
1032
+ "epoch": 0.5143094151804231,
1033
+ "grad_norm": 0.765625,
1034
+ "learning_rate": 1.9407829876923988e-05,
1035
+ "loss": 0.07,
1036
+ "num_input_tokens_seen": 200471392,
1037
+ "step": 1240
1038
+ },
1039
+ {
1040
+ "epoch": 0.5184570717544588,
1041
+ "grad_norm": 0.58203125,
1042
+ "learning_rate": 1.914477897388619e-05,
1043
+ "loss": 0.0491,
1044
+ "num_input_tokens_seen": 202067200,
1045
+ "step": 1250
1046
+ },
1047
+ {
1048
+ "epoch": 0.5226047283284944,
1049
+ "grad_norm": 0.984375,
1050
+ "learning_rate": 1.888187620902955e-05,
1051
+ "loss": 0.0619,
1052
+ "num_input_tokens_seen": 203693008,
1053
+ "step": 1260
1054
+ },
1055
+ {
1056
+ "epoch": 0.5267523849025301,
1057
+ "grad_norm": 0.55078125,
1058
+ "learning_rate": 1.861916712138576e-05,
1059
+ "loss": 0.0607,
1060
+ "num_input_tokens_seen": 205296720,
1061
+ "step": 1270
1062
+ },
1063
+ {
1064
+ "epoch": 0.5309000414765658,
1065
+ "grad_norm": 0.90625,
1066
+ "learning_rate": 1.8356697216438465e-05,
1067
+ "loss": 0.0716,
1068
+ "num_input_tokens_seen": 206884160,
1069
+ "step": 1280
1070
+ },
1071
+ {
1072
+ "epoch": 0.5350476980506014,
1073
+ "grad_norm": 0.53515625,
1074
+ "learning_rate": 1.8094511958240985e-05,
1075
+ "loss": 0.0465,
1076
+ "num_input_tokens_seen": 208524352,
1077
+ "step": 1290
1078
+ },
1079
+ {
1080
+ "epoch": 0.5391953546246371,
1081
+ "grad_norm": 0.5546875,
1082
+ "learning_rate": 1.783265676154119e-05,
1083
+ "loss": 0.0511,
1084
+ "num_input_tokens_seen": 210124256,
1085
+ "step": 1300
1086
+ },
1087
+ {
1088
+ "epoch": 0.5433430111986728,
1089
+ "grad_norm": 0.5390625,
1090
+ "learning_rate": 1.7571176983914942e-05,
1091
+ "loss": 0.0469,
1092
+ "num_input_tokens_seen": 211766032,
1093
+ "step": 1310
1094
+ },
1095
+ {
1096
+ "epoch": 0.5474906677727084,
1097
+ "grad_norm": 0.67578125,
1098
+ "learning_rate": 1.7310117917909407e-05,
1099
+ "loss": 0.0491,
1100
+ "num_input_tokens_seen": 213370896,
1101
+ "step": 1320
1102
+ },
1103
+ {
1104
+ "epoch": 0.5516383243467441,
1105
+ "grad_norm": 0.57421875,
1106
+ "learning_rate": 1.704952478319767e-05,
1107
+ "loss": 0.0625,
1108
+ "num_input_tokens_seen": 214955008,
1109
+ "step": 1330
1110
+ },
1111
+ {
1112
+ "epoch": 0.5557859809207798,
1113
+ "grad_norm": 0.58984375,
1114
+ "learning_rate": 1.6789442718745956e-05,
1115
+ "loss": 0.0457,
1116
+ "num_input_tokens_seen": 216503392,
1117
+ "step": 1340
1118
+ },
1119
+ {
1120
+ "epoch": 0.5599336374948154,
1121
+ "grad_norm": 1.203125,
1122
+ "learning_rate": 1.6529916774994766e-05,
1123
+ "loss": 0.0547,
1124
+ "num_input_tokens_seen": 218057744,
1125
+ "step": 1350
1126
+ },
1127
+ {
1128
+ "epoch": 0.5640812940688511,
1129
+ "grad_norm": 0.69140625,
1130
+ "learning_rate": 1.6270991906055517e-05,
1131
+ "loss": 0.0645,
1132
+ "num_input_tokens_seen": 219666784,
1133
+ "step": 1360
1134
+ },
1135
+ {
1136
+ "epoch": 0.5682289506428868,
1137
+ "grad_norm": 0.69921875,
1138
+ "learning_rate": 1.6012712961923666e-05,
1139
+ "loss": 0.054,
1140
+ "num_input_tokens_seen": 221234848,
1141
+ "step": 1370
1142
+ },
1143
+ {
1144
+ "epoch": 0.5723766072169224,
1145
+ "grad_norm": 0.71875,
1146
+ "learning_rate": 1.5755124680710005e-05,
1147
+ "loss": 0.0497,
1148
+ "num_input_tokens_seen": 222885040,
1149
+ "step": 1380
1150
+ },
1151
+ {
1152
+ "epoch": 0.5765242637909581,
1153
+ "grad_norm": 0.7109375,
1154
+ "learning_rate": 1.5498271680891274e-05,
1155
+ "loss": 0.056,
1156
+ "num_input_tokens_seen": 224548576,
1157
+ "step": 1390
1158
+ },
1159
+ {
1160
+ "epoch": 0.5806719203649938,
1161
+ "grad_norm": 0.9921875,
1162
+ "learning_rate": 1.5242198453581541e-05,
1163
+ "loss": 0.0534,
1164
+ "num_input_tokens_seen": 226222464,
1165
+ "step": 1400
1166
+ },
1167
+ {
1168
+ "epoch": 0.5848195769390294,
1169
+ "grad_norm": 0.419921875,
1170
+ "learning_rate": 1.498694935482559e-05,
1171
+ "loss": 0.0514,
1172
+ "num_input_tokens_seen": 227820832,
1173
+ "step": 1410
1174
+ },
1175
+ {
1176
+ "epoch": 0.5889672335130651,
1177
+ "grad_norm": 0.5390625,
1178
+ "learning_rate": 1.4732568597915749e-05,
1179
+ "loss": 0.0504,
1180
+ "num_input_tokens_seen": 229520608,
1181
+ "step": 1420
1182
+ },
1183
+ {
1184
+ "epoch": 0.5931148900871008,
1185
+ "grad_norm": 0.62109375,
1186
+ "learning_rate": 1.4479100245733438e-05,
1187
+ "loss": 0.0471,
1188
+ "num_input_tokens_seen": 231128896,
1189
+ "step": 1430
1190
+ },
1191
+ {
1192
+ "epoch": 0.5972625466611364,
1193
+ "grad_norm": 0.75390625,
1194
+ "learning_rate": 1.4226588203116716e-05,
1195
+ "loss": 0.0472,
1196
+ "num_input_tokens_seen": 232762928,
1197
+ "step": 1440
1198
+ },
1199
+ {
1200
+ "epoch": 0.6014102032351721,
1201
+ "grad_norm": 0.7734375,
1202
+ "learning_rate": 1.3975076209255321e-05,
1203
+ "loss": 0.0772,
1204
+ "num_input_tokens_seen": 234398016,
1205
+ "step": 1450
1206
+ },
1207
+ {
1208
+ "epoch": 0.6055578598092078,
1209
+ "grad_norm": 0.53125,
1210
+ "learning_rate": 1.3724607830114265e-05,
1211
+ "loss": 0.053,
1212
+ "num_input_tokens_seen": 235995488,
1213
+ "step": 1460
1214
+ },
1215
+ {
1216
+ "epoch": 0.6097055163832434,
1217
+ "grad_norm": 0.60546875,
1218
+ "learning_rate": 1.3475226450887546e-05,
1219
+ "loss": 0.0605,
1220
+ "num_input_tokens_seen": 237566320,
1221
+ "step": 1470
1222
+ },
1223
+ {
1224
+ "epoch": 0.6138531729572791,
1225
+ "grad_norm": 0.6796875,
1226
+ "learning_rate": 1.3226975268483107e-05,
1227
+ "loss": 0.0416,
1228
+ "num_input_tokens_seen": 239123808,
1229
+ "step": 1480
1230
+ },
1231
+ {
1232
+ "epoch": 0.6180008295313149,
1233
+ "grad_norm": 0.54296875,
1234
+ "learning_rate": 1.2979897284040433e-05,
1235
+ "loss": 0.0651,
1236
+ "num_input_tokens_seen": 240734672,
1237
+ "step": 1490
1238
+ },
1239
+ {
1240
+ "epoch": 0.6221484861053505,
1241
+ "grad_norm": 0.55078125,
1242
+ "learning_rate": 1.2734035295482044e-05,
1243
+ "loss": 0.0648,
1244
+ "num_input_tokens_seen": 242396032,
1245
+ "step": 1500
1246
+ },
1247
+ {
1248
+ "epoch": 0.6221484861053505,
1249
+ "eval_loss": 0.050693172961473465,
1250
+ "eval_runtime": 51.5616,
1251
+ "eval_samples_per_second": 60.452,
1252
+ "eval_steps_per_second": 1.901,
1253
+ "num_input_tokens_seen": 242396032,
1254
+ "step": 1500
1255
+ },
1256
+ {
1257
+ "epoch": 0.6262961426793862,
1258
+ "grad_norm": 0.515625,
1259
+ "learning_rate": 1.2489431890100223e-05,
1260
+ "loss": 0.0763,
1261
+ "num_input_tokens_seen": 244010816,
1262
+ "step": 1510
1263
+ },
1264
+ {
1265
+ "epoch": 0.6304437992534219,
1266
+ "grad_norm": 0.5078125,
1267
+ "learning_rate": 1.2246129437180198e-05,
1268
+ "loss": 0.0705,
1269
+ "num_input_tokens_seen": 245636640,
1270
+ "step": 1520
1271
+ },
1272
+ {
1273
+ "epoch": 0.6345914558274575,
1274
+ "grad_norm": 0.89453125,
1275
+ "learning_rate": 1.2004170080661054e-05,
1276
+ "loss": 0.0417,
1277
+ "num_input_tokens_seen": 247264032,
1278
+ "step": 1530
1279
+ },
1280
+ {
1281
+ "epoch": 0.6387391124014932,
1282
+ "grad_norm": 0.70703125,
1283
+ "learning_rate": 1.176359573183579e-05,
1284
+ "loss": 0.0563,
1285
+ "num_input_tokens_seen": 248895040,
1286
+ "step": 1540
1287
+ },
1288
+ {
1289
+ "epoch": 0.6428867689755289,
1290
+ "grad_norm": 0.86328125,
1291
+ "learning_rate": 1.1524448062091537e-05,
1292
+ "loss": 0.0567,
1293
+ "num_input_tokens_seen": 250514032,
1294
+ "step": 1550
1295
+ },
1296
+ {
1297
+ "epoch": 0.6470344255495645,
1298
+ "grad_norm": 0.8359375,
1299
+ "learning_rate": 1.1286768495691439e-05,
1300
+ "loss": 0.0487,
1301
+ "num_input_tokens_seen": 252089552,
1302
+ "step": 1560
1303
+ },
1304
+ {
1305
+ "epoch": 0.6511820821236002,
1306
+ "grad_norm": 0.47265625,
1307
+ "learning_rate": 1.1050598202599265e-05,
1308
+ "loss": 0.0518,
1309
+ "num_input_tokens_seen": 253733632,
1310
+ "step": 1570
1311
+ },
1312
+ {
1313
+ "epoch": 0.6553297386976359,
1314
+ "grad_norm": 0.6484375,
1315
+ "learning_rate": 1.0815978091348129e-05,
1316
+ "loss": 0.0548,
1317
+ "num_input_tokens_seen": 255366048,
1318
+ "step": 1580
1319
+ },
1320
+ {
1321
+ "epoch": 0.6594773952716715,
1322
+ "grad_norm": 0.75,
1323
+ "learning_rate": 1.0582948801954458e-05,
1324
+ "loss": 0.0653,
1325
+ "num_input_tokens_seen": 257013840,
1326
+ "step": 1590
1327
+ },
1328
+ {
1329
+ "epoch": 0.6636250518457072,
1330
+ "grad_norm": 0.4453125,
1331
+ "learning_rate": 1.035155069887846e-05,
1332
+ "loss": 0.0442,
1333
+ "num_input_tokens_seen": 258569696,
1334
+ "step": 1600
1335
+ },
1336
+ {
1337
+ "epoch": 0.6677727084197429,
1338
+ "grad_norm": 0.60546875,
1339
+ "learning_rate": 1.0121823864032383e-05,
1340
+ "loss": 0.0488,
1341
+ "num_input_tokens_seen": 260201856,
1342
+ "step": 1610
1343
+ },
1344
+ {
1345
+ "epoch": 0.6719203649937785,
1346
+ "grad_norm": 0.4765625,
1347
+ "learning_rate": 9.893808089837638e-06,
1348
+ "loss": 0.0397,
1349
+ "num_input_tokens_seen": 261772832,
1350
+ "step": 1620
1351
+ },
1352
+ {
1353
+ "epoch": 0.6760680215678142,
1354
+ "grad_norm": 0.361328125,
1355
+ "learning_rate": 9.66754287233214e-06,
1356
+ "loss": 0.0552,
1357
+ "num_input_tokens_seen": 263427808,
1358
+ "step": 1630
1359
+ },
1360
+ {
1361
+ "epoch": 0.6802156781418498,
1362
+ "grad_norm": 0.83203125,
1363
+ "learning_rate": 9.443067404328918e-06,
1364
+ "loss": 0.0625,
1365
+ "num_input_tokens_seen": 265071264,
1366
+ "step": 1640
1367
+ },
1368
+ {
1369
+ "epoch": 0.6843633347158855,
1370
+ "grad_norm": 0.4609375,
1371
+ "learning_rate": 9.220420568627313e-06,
1372
+ "loss": 0.0567,
1373
+ "num_input_tokens_seen": 266668784,
1374
+ "step": 1650
1375
+ },
1376
+ {
1377
+ "epoch": 0.6885109912899212,
1378
+ "grad_norm": 0.546875,
1379
+ "learning_rate": 8.999640931277825e-06,
1380
+ "loss": 0.0477,
1381
+ "num_input_tokens_seen": 268367856,
1382
+ "step": 1660
1383
+ },
1384
+ {
1385
+ "epoch": 0.6926586478639568,
1386
+ "grad_norm": 0.66796875,
1387
+ "learning_rate": 8.780766734901851e-06,
1388
+ "loss": 0.0408,
1389
+ "num_input_tokens_seen": 269965632,
1390
+ "step": 1670
1391
+ },
1392
+ {
1393
+ "epoch": 0.6968063044379925,
1394
+ "grad_norm": 0.70703125,
1395
+ "learning_rate": 8.563835892067446e-06,
1396
+ "loss": 0.0677,
1397
+ "num_input_tokens_seen": 271631968,
1398
+ "step": 1680
1399
+ },
1400
+ {
1401
+ "epoch": 0.7009539610120282,
1402
+ "grad_norm": 0.734375,
1403
+ "learning_rate": 8.348885978722252e-06,
1404
+ "loss": 0.0454,
1405
+ "num_input_tokens_seen": 273246624,
1406
+ "step": 1690
1407
+ },
1408
+ {
1409
+ "epoch": 0.7051016175860638,
1410
+ "grad_norm": 0.5234375,
1411
+ "learning_rate": 8.135954227684725e-06,
1412
+ "loss": 0.0671,
1413
+ "num_input_tokens_seen": 274826768,
1414
+ "step": 1700
1415
+ },
1416
+ {
1417
+ "epoch": 0.7092492741600995,
1418
+ "grad_norm": 0.451171875,
1419
+ "learning_rate": 7.925077522194797e-06,
1420
+ "loss": 0.0576,
1421
+ "num_input_tokens_seen": 276517456,
1422
+ "step": 1710
1423
+ },
1424
+ {
1425
+ "epoch": 0.7133969307341352,
1426
+ "grad_norm": 0.515625,
1427
+ "learning_rate": 7.716292389525135e-06,
1428
+ "loss": 0.0479,
1429
+ "num_input_tokens_seen": 278157936,
1430
+ "step": 1720
1431
+ },
1432
+ {
1433
+ "epoch": 0.7175445873081708,
1434
+ "grad_norm": 0.62109375,
1435
+ "learning_rate": 7.5096349946539735e-06,
1436
+ "loss": 0.0521,
1437
+ "num_input_tokens_seen": 279750640,
1438
+ "step": 1730
1439
+ },
1440
+ {
1441
+ "epoch": 0.7216922438822065,
1442
+ "grad_norm": 0.5859375,
1443
+ "learning_rate": 7.305141134000804e-06,
1444
+ "loss": 0.048,
1445
+ "num_input_tokens_seen": 281405344,
1446
+ "step": 1740
1447
+ },
1448
+ {
1449
+ "epoch": 0.7258399004562422,
1450
+ "grad_norm": 0.6875,
1451
+ "learning_rate": 7.102846229225813e-06,
1452
+ "loss": 0.0452,
1453
+ "num_input_tokens_seen": 283103808,
1454
+ "step": 1750
1455
+ },
1456
+ {
1457
+ "epoch": 0.7299875570302778,
1458
+ "grad_norm": 0.62109375,
1459
+ "learning_rate": 6.902785321094301e-06,
1460
+ "loss": 0.0391,
1461
+ "num_input_tokens_seen": 284686976,
1462
+ "step": 1760
1463
+ },
1464
+ {
1465
+ "epoch": 0.7341352136043136,
1466
+ "grad_norm": 0.76171875,
1467
+ "learning_rate": 6.7049930634070325e-06,
1468
+ "loss": 0.0487,
1469
+ "num_input_tokens_seen": 286315792,
1470
+ "step": 1770
1471
+ },
1472
+ {
1473
+ "epoch": 0.7382828701783493,
1474
+ "grad_norm": 0.455078125,
1475
+ "learning_rate": 6.509503716997649e-06,
1476
+ "loss": 0.049,
1477
+ "num_input_tokens_seen": 287958704,
1478
+ "step": 1780
1479
+ },
1480
+ {
1481
+ "epoch": 0.7424305267523849,
1482
+ "grad_norm": 0.73046875,
1483
+ "learning_rate": 6.316351143798141e-06,
1484
+ "loss": 0.0669,
1485
+ "num_input_tokens_seen": 289607936,
1486
+ "step": 1790
1487
+ },
1488
+ {
1489
+ "epoch": 0.7465781833264206,
1490
+ "grad_norm": 0.91796875,
1491
+ "learning_rate": 6.125568800973372e-06,
1492
+ "loss": 0.0554,
1493
+ "num_input_tokens_seen": 291205392,
1494
+ "step": 1800
1495
+ },
1496
+ {
1497
+ "epoch": 0.7465781833264206,
1498
+ "eval_loss": 0.049129463732242584,
1499
+ "eval_runtime": 51.7862,
1500
+ "eval_samples_per_second": 60.19,
1501
+ "eval_steps_per_second": 1.892,
1502
+ "num_input_tokens_seen": 291205392,
1503
+ "step": 1800
1504
+ },
1505
+ {
1506
+ "epoch": 0.7507258399004563,
1507
+ "grad_norm": 0.56640625,
1508
+ "learning_rate": 5.9371897351258075e-06,
1509
+ "loss": 0.0559,
1510
+ "num_input_tokens_seen": 292866352,
1511
+ "step": 1810
1512
+ },
1513
+ {
1514
+ "epoch": 0.7548734964744919,
1515
+ "grad_norm": 0.68359375,
1516
+ "learning_rate": 5.751246576571274e-06,
1517
+ "loss": 0.064,
1518
+ "num_input_tokens_seen": 294510528,
1519
+ "step": 1820
1520
+ },
1521
+ {
1522
+ "epoch": 0.7590211530485276,
1523
+ "grad_norm": 0.7890625,
1524
+ "learning_rate": 5.567771533686865e-06,
1525
+ "loss": 0.0563,
1526
+ "num_input_tokens_seen": 296088976,
1527
+ "step": 1830
1528
+ },
1529
+ {
1530
+ "epoch": 0.7631688096225633,
1531
+ "grad_norm": 0.4921875,
1532
+ "learning_rate": 5.386796387331938e-06,
1533
+ "loss": 0.0543,
1534
+ "num_input_tokens_seen": 297673328,
1535
+ "step": 1840
1536
+ },
1537
+ {
1538
+ "epoch": 0.7673164661965989,
1539
+ "grad_norm": 0.90234375,
1540
+ "learning_rate": 5.208352485343113e-06,
1541
+ "loss": 0.0556,
1542
+ "num_input_tokens_seen": 299376752,
1543
+ "step": 1850
1544
+ },
1545
+ {
1546
+ "epoch": 0.7714641227706346,
1547
+ "grad_norm": 0.53125,
1548
+ "learning_rate": 5.032470737104378e-06,
1549
+ "loss": 0.0568,
1550
+ "num_input_tokens_seen": 301050928,
1551
+ "step": 1860
1552
+ },
1553
+ {
1554
+ "epoch": 0.7756117793446703,
1555
+ "grad_norm": 0.87109375,
1556
+ "learning_rate": 4.859181608193031e-06,
1557
+ "loss": 0.0478,
1558
+ "num_input_tokens_seen": 302644848,
1559
+ "step": 1870
1560
+ },
1561
+ {
1562
+ "epoch": 0.7797594359187059,
1563
+ "grad_norm": 0.55859375,
1564
+ "learning_rate": 4.688515115102579e-06,
1565
+ "loss": 0.0438,
1566
+ "num_input_tokens_seen": 304286592,
1567
+ "step": 1880
1568
+ },
1569
+ {
1570
+ "epoch": 0.7839070924927416,
1571
+ "grad_norm": 0.66015625,
1572
+ "learning_rate": 4.520500820043374e-06,
1573
+ "loss": 0.0524,
1574
+ "num_input_tokens_seen": 305937648,
1575
+ "step": 1890
1576
+ },
1577
+ {
1578
+ "epoch": 0.7880547490667773,
1579
+ "grad_norm": 0.55859375,
1580
+ "learning_rate": 4.355167825821957e-06,
1581
+ "loss": 0.066,
1582
+ "num_input_tokens_seen": 307573472,
1583
+ "step": 1900
1584
+ },
1585
+ {
1586
+ "epoch": 0.7922024056408129,
1587
+ "grad_norm": 0.73046875,
1588
+ "learning_rate": 4.192544770800002e-06,
1589
+ "loss": 0.0461,
1590
+ "num_input_tokens_seen": 309152720,
1591
+ "step": 1910
1592
+ },
1593
+ {
1594
+ "epoch": 0.7963500622148486,
1595
+ "grad_norm": 0.9296875,
1596
+ "learning_rate": 4.032659823933656e-06,
1597
+ "loss": 0.0531,
1598
+ "num_input_tokens_seen": 310766416,
1599
+ "step": 1920
1600
+ },
1601
+ {
1602
+ "epoch": 0.8004977187888843,
1603
+ "grad_norm": 0.318359375,
1604
+ "learning_rate": 3.875540679894243e-06,
1605
+ "loss": 0.0377,
1606
+ "num_input_tokens_seen": 312403088,
1607
+ "step": 1930
1608
+ },
1609
+ {
1610
+ "epoch": 0.8046453753629199,
1611
+ "grad_norm": 0.578125,
1612
+ "learning_rate": 3.721214554271082e-06,
1613
+ "loss": 0.057,
1614
+ "num_input_tokens_seen": 314029904,
1615
+ "step": 1940
1616
+ },
1617
+ {
1618
+ "epoch": 0.8087930319369556,
1619
+ "grad_norm": 0.5234375,
1620
+ "learning_rate": 3.569708178857312e-06,
1621
+ "loss": 0.0463,
1622
+ "num_input_tokens_seen": 315638752,
1623
+ "step": 1950
1624
+ },
1625
+ {
1626
+ "epoch": 0.8129406885109913,
1627
+ "grad_norm": 0.56640625,
1628
+ "learning_rate": 3.4210477970194945e-06,
1629
+ "loss": 0.058,
1630
+ "num_input_tokens_seen": 317249712,
1631
+ "step": 1960
1632
+ },
1633
+ {
1634
+ "epoch": 0.8170883450850269,
1635
+ "grad_norm": 0.80078125,
1636
+ "learning_rate": 3.2752591591518666e-06,
1637
+ "loss": 0.0615,
1638
+ "num_input_tokens_seen": 318835520,
1639
+ "step": 1970
1640
+ },
1641
+ {
1642
+ "epoch": 0.8212360016590626,
1643
+ "grad_norm": 0.71484375,
1644
+ "learning_rate": 3.1323675182159354e-06,
1645
+ "loss": 0.0449,
1646
+ "num_input_tokens_seen": 320467712,
1647
+ "step": 1980
1648
+ },
1649
+ {
1650
+ "epoch": 0.8253836582330983,
1651
+ "grad_norm": 0.5625,
1652
+ "learning_rate": 2.992397625366237e-06,
1653
+ "loss": 0.0544,
1654
+ "num_input_tokens_seen": 322067104,
1655
+ "step": 1990
1656
+ },
1657
+ {
1658
+ "epoch": 0.8295313148071339,
1659
+ "grad_norm": 0.8984375,
1660
+ "learning_rate": 2.8553737256630753e-06,
1661
+ "loss": 0.0478,
1662
+ "num_input_tokens_seen": 323681856,
1663
+ "step": 2000
1664
+ },
1665
+ {
1666
+ "epoch": 0.8336789713811696,
1667
+ "grad_norm": 0.458984375,
1668
+ "learning_rate": 2.721319553872852e-06,
1669
+ "loss": 0.0502,
1670
+ "num_input_tokens_seen": 325343216,
1671
+ "step": 2010
1672
+ },
1673
+ {
1674
+ "epoch": 0.8378266279552053,
1675
+ "grad_norm": 0.53125,
1676
+ "learning_rate": 2.590258330356832e-06,
1677
+ "loss": 0.0458,
1678
+ "num_input_tokens_seen": 326946720,
1679
+ "step": 2020
1680
+ },
1681
+ {
1682
+ "epoch": 0.841974284529241,
1683
+ "grad_norm": 0.5078125,
1684
+ "learning_rate": 2.462212757048992e-06,
1685
+ "loss": 0.0589,
1686
+ "num_input_tokens_seen": 328553024,
1687
+ "step": 2030
1688
+ },
1689
+ {
1690
+ "epoch": 0.8461219411032767,
1691
+ "grad_norm": 0.71484375,
1692
+ "learning_rate": 2.3372050135236846e-06,
1693
+ "loss": 0.0473,
1694
+ "num_input_tokens_seen": 330170176,
1695
+ "step": 2040
1696
+ },
1697
+ {
1698
+ "epoch": 0.8502695976773124,
1699
+ "grad_norm": 0.79296875,
1700
+ "learning_rate": 2.2152567531537694e-06,
1701
+ "loss": 0.0623,
1702
+ "num_input_tokens_seen": 331801536,
1703
+ "step": 2050
1704
+ },
1705
+ {
1706
+ "epoch": 0.854417254251348,
1707
+ "grad_norm": 0.671875,
1708
+ "learning_rate": 2.0963890993599034e-06,
1709
+ "loss": 0.0553,
1710
+ "num_input_tokens_seen": 333424704,
1711
+ "step": 2060
1712
+ },
1713
+ {
1714
+ "epoch": 0.8585649108253837,
1715
+ "grad_norm": 0.70703125,
1716
+ "learning_rate": 1.9806226419516195e-06,
1717
+ "loss": 0.06,
1718
+ "num_input_tokens_seen": 335002400,
1719
+ "step": 2070
1720
+ },
1721
+ {
1722
+ "epoch": 0.8627125673994194,
1723
+ "grad_norm": 0.78125,
1724
+ "learning_rate": 1.867977433560817e-06,
1725
+ "loss": 0.0413,
1726
+ "num_input_tokens_seen": 336586720,
1727
+ "step": 2080
1728
+ },
1729
+ {
1730
+ "epoch": 0.866860223973455,
1731
+ "grad_norm": 0.64453125,
1732
+ "learning_rate": 1.7584729861683603e-06,
1733
+ "loss": 0.0441,
1734
+ "num_input_tokens_seen": 338226048,
1735
+ "step": 2090
1736
+ },
1737
+ {
1738
+ "epoch": 0.8710078805474907,
1739
+ "grad_norm": 0.9140625,
1740
+ "learning_rate": 1.6521282677242468e-06,
1741
+ "loss": 0.0435,
1742
+ "num_input_tokens_seen": 339841056,
1743
+ "step": 2100
1744
+ },
1745
+ {
1746
+ "epoch": 0.8710078805474907,
1747
+ "eval_loss": 0.04848345369100571,
1748
+ "eval_runtime": 51.7331,
1749
+ "eval_samples_per_second": 60.252,
1750
+ "eval_steps_per_second": 1.894,
1751
+ "num_input_tokens_seen": 339841056,
1752
+ "step": 2100
1753
+ },
1754
+ {
1755
+ "epoch": 0.8751555371215264,
1756
+ "grad_norm": 0.447265625,
1757
+ "learning_rate": 1.548961698862077e-06,
1758
+ "loss": 0.0487,
1759
+ "num_input_tokens_seen": 341502688,
1760
+ "step": 2110
1761
+ },
1762
+ {
1763
+ "epoch": 0.879303193695562,
1764
+ "grad_norm": 0.78515625,
1765
+ "learning_rate": 1.4489911497082877e-06,
1766
+ "loss": 0.0512,
1767
+ "num_input_tokens_seen": 343140656,
1768
+ "step": 2120
1769
+ },
1770
+ {
1771
+ "epoch": 0.8834508502695977,
1772
+ "grad_norm": 1.1171875,
1773
+ "learning_rate": 1.3522339367867553e-06,
1774
+ "loss": 0.0539,
1775
+ "num_input_tokens_seen": 344755872,
1776
+ "step": 2130
1777
+ },
1778
+ {
1779
+ "epoch": 0.8875985068436334,
1780
+ "grad_norm": 0.51171875,
1781
+ "learning_rate": 1.2587068200193065e-06,
1782
+ "loss": 0.0396,
1783
+ "num_input_tokens_seen": 346370080,
1784
+ "step": 2140
1785
+ },
1786
+ {
1787
+ "epoch": 0.891746163417669,
1788
+ "grad_norm": 0.68359375,
1789
+ "learning_rate": 1.1684259998226044e-06,
1790
+ "loss": 0.0536,
1791
+ "num_input_tokens_seen": 348025424,
1792
+ "step": 2150
1793
+ },
1794
+ {
1795
+ "epoch": 0.8958938199917047,
1796
+ "grad_norm": 0.50390625,
1797
+ "learning_rate": 1.081407114302e-06,
1798
+ "loss": 0.0444,
1799
+ "num_input_tokens_seen": 349610864,
1800
+ "step": 2160
1801
+ },
1802
+ {
1803
+ "epoch": 0.9000414765657404,
1804
+ "grad_norm": 0.5078125,
1805
+ "learning_rate": 9.976652365427242e-07,
1806
+ "loss": 0.0437,
1807
+ "num_input_tokens_seen": 351226816,
1808
+ "step": 2170
1809
+ },
1810
+ {
1811
+ "epoch": 0.904189133139776,
1812
+ "grad_norm": 0.439453125,
1813
+ "learning_rate": 9.172148719990237e-07,
1814
+ "loss": 0.0608,
1815
+ "num_input_tokens_seen": 352894160,
1816
+ "step": 2180
1817
+ },
1818
+ {
1819
+ "epoch": 0.9083367897138117,
1820
+ "grad_norm": 0.67578125,
1821
+ "learning_rate": 8.400699559815506e-07,
1822
+ "loss": 0.0472,
1823
+ "num_input_tokens_seen": 354495920,
1824
+ "step": 2190
1825
+ },
1826
+ {
1827
+ "epoch": 0.9124844462878474,
1828
+ "grad_norm": 0.828125,
1829
+ "learning_rate": 7.662438512435533e-07,
1830
+ "loss": 0.065,
1831
+ "num_input_tokens_seen": 356095968,
1832
+ "step": 2200
1833
+ },
1834
+ {
1835
+ "epoch": 0.916632102861883,
1836
+ "grad_norm": 0.796875,
1837
+ "learning_rate": 6.957493456662301e-07,
1838
+ "loss": 0.0527,
1839
+ "num_input_tokens_seen": 357755280,
1840
+ "step": 2210
1841
+ },
1842
+ {
1843
+ "epoch": 0.9207797594359187,
1844
+ "grad_norm": 0.462890625,
1845
+ "learning_rate": 6.285986500436525e-07,
1846
+ "loss": 0.0423,
1847
+ "num_input_tokens_seen": 359320080,
1848
+ "step": 2220
1849
+ },
1850
+ {
1851
+ "epoch": 0.9249274160099544,
1852
+ "grad_norm": 0.5,
1853
+ "learning_rate": 5.648033959676658e-07,
1854
+ "loss": 0.0468,
1855
+ "num_input_tokens_seen": 360913328,
1856
+ "step": 2230
1857
+ },
1858
+ {
1859
+ "epoch": 0.92907507258399,
1860
+ "grad_norm": 0.73828125,
1861
+ "learning_rate": 5.043746338131072e-07,
1862
+ "loss": 0.0568,
1863
+ "num_input_tokens_seen": 362546480,
1864
+ "step": 2240
1865
+ },
1866
+ {
1867
+ "epoch": 0.9332227291580257,
1868
+ "grad_norm": 0.45703125,
1869
+ "learning_rate": 4.4732283082369767e-07,
1870
+ "loss": 0.0376,
1871
+ "num_input_tokens_seen": 364148224,
1872
+ "step": 2250
1873
+ },
1874
+ {
1875
+ "epoch": 0.9373703857320614,
1876
+ "grad_norm": 0.6328125,
1877
+ "learning_rate": 3.9365786929894455e-07,
1878
+ "loss": 0.0513,
1879
+ "num_input_tokens_seen": 365695088,
1880
+ "step": 2260
1881
+ },
1882
+ {
1883
+ "epoch": 0.941518042306097,
1884
+ "grad_norm": 0.546875,
1885
+ "learning_rate": 3.43389044882374e-07,
1886
+ "loss": 0.057,
1887
+ "num_input_tokens_seen": 367280736,
1888
+ "step": 2270
1889
+ },
1890
+ {
1891
+ "epoch": 0.9456656988801327,
1892
+ "grad_norm": 0.58203125,
1893
+ "learning_rate": 2.965250649513629e-07,
1894
+ "loss": 0.0376,
1895
+ "num_input_tokens_seen": 368861360,
1896
+ "step": 2280
1897
+ },
1898
+ {
1899
+ "epoch": 0.9498133554541683,
1900
+ "grad_norm": 0.59765625,
1901
+ "learning_rate": 2.5307404710889217e-07,
1902
+ "loss": 0.0481,
1903
+ "num_input_tokens_seen": 370431952,
1904
+ "step": 2290
1905
+ },
1906
+ {
1907
+ "epoch": 0.953961012028204,
1908
+ "grad_norm": 0.455078125,
1909
+ "learning_rate": 2.1304351777743816e-07,
1910
+ "loss": 0.0448,
1911
+ "num_input_tokens_seen": 372061472,
1912
+ "step": 2300
1913
+ },
1914
+ {
1915
+ "epoch": 0.9581086686022398,
1916
+ "grad_norm": 0.53515625,
1917
+ "learning_rate": 1.7644041089527332e-07,
1918
+ "loss": 0.0726,
1919
+ "num_input_tokens_seen": 373691376,
1920
+ "step": 2310
1921
+ },
1922
+ {
1923
+ "epoch": 0.9622563251762754,
1924
+ "grad_norm": 0.640625,
1925
+ "learning_rate": 1.4327106671540248e-07,
1926
+ "loss": 0.0348,
1927
+ "num_input_tokens_seen": 375329184,
1928
+ "step": 2320
1929
+ },
1930
+ {
1931
+ "epoch": 0.9664039817503111,
1932
+ "grad_norm": 0.4453125,
1933
+ "learning_rate": 1.1354123070732137e-07,
1934
+ "loss": 0.0642,
1935
+ "num_input_tokens_seen": 376895712,
1936
+ "step": 2330
1937
+ },
1938
+ {
1939
+ "epoch": 0.9705516383243468,
1940
+ "grad_norm": 0.90625,
1941
+ "learning_rate": 8.725605256180602e-08,
1942
+ "loss": 0.0483,
1943
+ "num_input_tokens_seen": 378486272,
1944
+ "step": 2340
1945
+ },
1946
+ {
1947
+ "epoch": 0.9746992948983824,
1948
+ "grad_norm": 0.4921875,
1949
+ "learning_rate": 6.442008529891075e-08,
1950
+ "loss": 0.0429,
1951
+ "num_input_tokens_seen": 380094304,
1952
+ "step": 2350
1953
+ },
1954
+ {
1955
+ "epoch": 0.9788469514724181,
1956
+ "grad_norm": 0.498046875,
1957
+ "learning_rate": 4.503728447930566e-08,
1958
+ "loss": 0.0356,
1959
+ "num_input_tokens_seen": 381704560,
1960
+ "step": 2360
1961
+ },
1962
+ {
1963
+ "epoch": 0.9829946080464538,
1964
+ "grad_norm": 0.404296875,
1965
+ "learning_rate": 2.9111007519113665e-08,
1966
+ "loss": 0.0359,
1967
+ "num_input_tokens_seen": 383324784,
1968
+ "step": 2370
1969
+ },
1970
+ {
1971
+ "epoch": 0.9871422646204894,
1972
+ "grad_norm": 0.57421875,
1973
+ "learning_rate": 1.6644013108342294e-08,
1974
+ "loss": 0.0454,
1975
+ "num_input_tokens_seen": 384918032,
1976
+ "step": 2380
1977
+ },
1978
+ {
1979
+ "epoch": 0.9912899211945251,
1980
+ "grad_norm": 0.3828125,
1981
+ "learning_rate": 7.638460733043751e-09,
1982
+ "loss": 0.0433,
1983
+ "num_input_tokens_seen": 386639824,
1984
+ "step": 2390
1985
+ },
1986
+ {
1987
+ "epoch": 0.9954375777685608,
1988
+ "grad_norm": 0.84375,
1989
+ "learning_rate": 2.0959103012518913e-09,
1990
+ "loss": 0.067,
1991
+ "num_input_tokens_seen": 388287472,
1992
+ "step": 2400
1993
+ },
1994
+ {
1995
+ "epoch": 0.9954375777685608,
1996
+ "eval_loss": 0.04846753552556038,
1997
+ "eval_runtime": 52.7044,
1998
+ "eval_samples_per_second": 59.141,
1999
+ "eval_steps_per_second": 1.859,
2000
+ "num_input_tokens_seen": 388287472,
2001
+ "step": 2400
2002
+ },
2003
+ {
2004
+ "epoch": 0.9995852343425964,
2005
+ "grad_norm": 0.6953125,
2006
+ "learning_rate": 1.732187278280506e-11,
2007
+ "loss": 0.0414,
2008
+ "num_input_tokens_seen": 389830288,
2009
+ "step": 2410
2010
+ }
2011
+ ],
2012
+ "logging_steps": 10,
2013
+ "max_steps": 2411,
2014
+ "num_input_tokens_seen": 389993424,
2015
+ "num_train_epochs": 1,
2016
+ "save_steps": 300,
2017
+ "stateful_callbacks": {
2018
+ "TrainerControl": {
2019
+ "args": {
2020
+ "should_epoch_stop": false,
2021
+ "should_evaluate": false,
2022
+ "should_log": false,
2023
+ "should_save": true,
2024
+ "should_training_stop": true
2025
+ },
2026
+ "attributes": {}
2027
+ }
2028
+ },
2029
+ "total_flos": 2.1949017560795054e+18,
2030
+ "train_batch_size": 16,
2031
+ "trial_name": null,
2032
+ "trial_params": null
2033
+ }